Preprint
Jul 2026
Even More Deception: Objective Misalignment in Mixed-Motive LLM Multi-Agent Systems
It is suggested that even subtle objective misalignment can profoundly affect collective decision-making, highlighting the need for effective mitigation strategies for LLM-based multi-agent systems.
Marylou Fauchard, Florian Carichon, Margarida Carvalho et al.
· 0 citations